Imputing missing counts for waterbird species: A comparison of methods for zero-inflated biodiversity monitoring data
Abstract
Species monitoring programmes regularly encounter missing data, which complicates tasks such as estimating population size or detecting temporal trends. Selecting an imputation method suited to the properties of the data is therefore an important practical challenge, particularly for species exhibiting overdispersion and zero-inflation. We compare seventeen imputation methods, comprising thirteen Poisson-based statistical models (accounting for overdispersion and zero-inflation, with fixed, random and multivariate structures) and four contrast-based approaches (LORI, MICE, missForest, correspondence analysis). Using four complete monitoring datasets of waterbird species surveyed across France and Italy over 21 years, illustrating a variety of abundance distributions, we introduced missing observations under a realistic Missing At Random mechanism, at rates from 5% to 70%. We evaluated all methods on computational burden, prediction accuracy for positive and null counts, quantification of uncertainty, and accuracy of population-size estimates. No single method dominates across all criteria. Statistical models and contrast-based approaches yield similar point predictions, but only statistical models provide a genuine measure of uncertainty. Models that jointly account for overdispersion and zero-inflation perform best at predicting zero counts and achieving reliable prediction intervals, and the most suitable method ultimately depends on the abundance distribution of the target species. These results provide practical guidance for ecologists selecting an imputation strategy for incomplete count data, highlighting the trade-offs between predictive accuracy, computational cost, and the ability to propagate uncertainty through subsequent ecological analyses such as population-trend estimation.
Related
- Separating Faces in ARMS Metabarcoding Improves Marine Biodiversity Monitoring: A Comparison Across Protocols, Experimental Designs and Photographic Surveys
- City life: airborne DNA metagenomic biodiversity monitoring reveals dynamic changes across time and space
- National-scale acoustic monitoring of avian biodiversity and migration
- Remote sensing and the EU nature restoration Regulation: monitoring biodiversity indicators for integrated forest management
- Monitoring major biodiversity stronghold in war zones: Model predicts Lake Chad remains Africa’s most important wetland for waterbirds
BibTeX
@misc{bricout2026imputing,
title = {{Imputing missing counts for waterbird species: A comparison of methods for zero-inflated biodiversity monitoring data}},
author = {Barbara Bricout and Laura Dami and Pierre Defos Du Rau and Sophie Donnet and Thomas Galewski and Stéphane Robin},
howpublished = {HAL},
year = {2026},
month = sep,
doi = {10.64898/2026.09.24.753523},
url = {https://hal.science/hal-05830347v1},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Imputing missing counts for waterbird species: A comparison of methods for zero-inflated biodiversity monitoring data
AU - Barbara Bricout
AU - Laura Dami
AU - Pierre Defos Du Rau
AU - Sophie Donnet
AU - Thomas Galewski
AU - Stéphane Robin
PY - 2026
DA - 2026/09/24
PB - HAL
DO - 10.64898/2026.09.24.753523
UR - https://hal.science/hal-05830347v1
AB - Species monitoring programmes regularly encounter missing data, which complicates tasks such as estimating population size or detecting temporal trends. Selecting an imputation method suited to the properties of the data is therefore an important practical challenge, particularly for species exhibiting overdispersion and zero-inflation. We compare seventeen imputation methods, comprising thirteen Poisson-based statistical models (accounting for overdispersion and zero-inflation, with fixed, random and multivariate structures) and four contrast-based approaches (LORI, MICE, missForest, correspondence analysis). Using four complete monitoring datasets of waterbird species surveyed across France and Italy over 21 years, illustrating a variety of abundance distributions, we introduced missing observations under a realistic Missing At Random mechanism, at rates from 5% to 70%. We evaluated all methods on computational burden, prediction accuracy for positive and null counts, quantification of uncertainty, and accuracy of population-size estimates. No single method dominates across all criteria. Statistical models and contrast-based approaches yield similar point predictions, but only statistical models provide a genuine measure of uncertainty. Models that jointly account for overdispersion and zero-inflation perform best at predicting zero counts and achieving reliable prediction intervals, and the most suitable method ultimately depends on the abundance distribution of the target species. These results provide practical guidance for ecologists selecting an imputation strategy for incomplete count data, highlighting the trade-offs between predictive accuracy, computational cost, and the ability to propagate uncertainty through subsequent ecological analyses such as population-trend estimation.
ER -